Recently, I completed a server-side conversion tracking system that connects Meta Ads, LINE Official Account, and n8n automation workflows. The system captures actual LINE friend additions and sends them directly to Meta through the Conversions API (CAPI), significantly improving attribution accuracy. Unlike traditional browser-based pixel tracking, this architecture is resilient to ad blockers, cookie restrictions, and browser privacy changes. Using n8n enabled rapid development, lower operational costs, and easier maintenance compared to building and managing a custom backend service. The workflow integrates webhooks, event processing, data transformation, and Meta server-side event delivery in a scalable architecture. This approach helps advertising campaigns optimize toward real business outcomes rather than simple page visits or button clicks. I specialize in building automation-driven systems that combine AI, APIs, cloud infrastructure, and marketing technology into production-ready solutions.

4 days in. We're almost at 50 members — here's what happens when we hit it. At 50 members, we turn on begin our monthly workshops. These aren't recorded courses. They're live sessions where I break down one thing all the way down — the stuff I normally only teach paid consulting clients: - How to build an offer people actually buy - What's selling right now with AI (and what's already dead) - How to find clients — the exact channels and scripts that work today - How to actually build the thing — start to finish, no hand-waving One topic per session. Deep, current, and tactical enough that you can go do it the same day. We're a handful of members away. When we cross 50, workshops go live. Two things, because I don't want you to miss this: 1. You're still on founders pricing — but not for long. The price goes up as we grow. Everyone who's in now is locked at the founding rate for as long as they stay. The people who join next month will pay more for the same room. 2. If you've been waiting for a "reason," this is it. The workshops alone are worth more than the entire membership. And you'll be in before the price moves. The people who win with AI aren't the ones with the most information. They're the ones in the room, doing the reps, getting corrected fast. That room exists now. And it's about to get a lot more valuable. [Join before the price goes up → https://www.skool.com/theaiaccelerator/about] See you on the first workshop. — Nick

I'm currently available for freelance projects, contract work, and full time software engineering roles. Over the past few years, I've worked with startups and companies building AI powered products, web platforms, mobile applications, automation systems, chatbots, and voice AI solutions. My experience spans the entire product lifecycle from planning and architecture to development, deployment, and scaling. Some of the areas I've worked in include: • AI agents and multi-agent systems using LangGraph, AutoGen, CrewAI, and ReAct • Generative AI applications powered by OpenAI, Claude, DeepSeek, and Hugging Face • RAG systems, AI assistants, and custom chatbot solutions • Voice AI and IVR platforms using Vapi AI, Retell AI, and Twilio • Workflow automation with n8n, Zapier, Make.com, and custom API integrations • Full-stack web development with Next.js, React, and Vue.js • Cross-platform mobile development with React Native and Expo • Computer vision, OCR, AI avatars, and media-generation applications Tech Stack: Python, TypeScript, JavaScript, Next.js, React, Vue.js, React Native, LangChain, LangGraph, OpenAI, Claude, DeepSeek, Hugging Face, n8n, Zapier, Make.com, Twilio, Vapi AI, and Retell AI. I've had the opportunity to work on projects for companies across a variety of industries and collaborate with distributed teams in different parts of the world. I'm comfortable working across time zones and can provide overlapping hours with teams in North America, Europe, and Asia. If you're looking for an engineer who can help build, launch, or scale AI products, web applications, mobile apps, or automation solutions, I'd be happy to connect. Feel free to send me a message I'd love to learn more about your project or team.

I just asked Claude Code to read every company in Y Combinator and show me the AI agent startups under 10 people. Y Combinator doesn't have an API. I'm not scraping their site. It came back in 50 milliseconds — none of it hit my context window. The way I'm doing this is a CLI. Not an API. Not an MCP server. A CLI. And the tool I'm using in this video lets you build one for any website on the internet — in about 90 minutes, hands-off — even sites with no API and no MCP server. In this video I break down: - The real reason every serious AI company is shipping a CLI in 2026 (Claude Code, Codex, gh, Stripe, Playwright, gws — they're all CLIs) - API vs MCP vs CLI — and why MCP is silently eating your context window (Anthropic shipped Tool Search Tool to fix this — that tells you everything) - The open-source tool that turns ANY website into a CLI your agent can drive - The full Y Combinator directory build, start to finish — 5,887 companies, 7 features no existing tool has 📎 Pinned below — full step-by-step guide PDF with every install command, the kickoff prompt, the factory phases, and the exact demo queries from the video. 🎁 While you're here: Outskill is running a free 2-day Claude-A-Thon this weekend — deep dive on Claude + 10 other AI tools, mentored by leaders from Microsoft, Google, Amazon, and Nvidia. First 1,000 seats are free: 👉 https://links.outskill.com/NICPU This pairs perfectly with the video — if you're going to build CLIs for your own stack, you want to know what Claude can actually do first. Drop a comment with the website you wish your agent could use that doesn't have an API. If a few of you land on the same one, I'll build the CLI on stream. [Watch the video here ▶️]

Everyone is hiring one AI tool at a time. I built a whole company instead — 147 agents across 14 divisions, all running inside a single workspace, all open source, all deployed with a single prompt. In this video I break down the exact 4-agent SDR team I'm running every Monday morning — Outbound Strategist, Account Strategist, Sales Outreach, and Reality Checker — that scrapes real data off LinkedIn, X, and company sites, drafts personalized cold emails, and kills anything that smells like AI slop before it reaches my sent folder. The full stack costs about $6/month and runs the whole thing on autopilot. What you'll learn: - How to install all 147 agents in one prompt - Deploying OpenClaw on Hostinger (one-click setup) - Wiring in OpenRouter (300+ models, one API key, free tier) - The Apify plugin that gives your agents real-world data - The exact Monday Morning SDR workflow (prompt included) 📎 I put together a full step-by-step guide with every command and prompt from the video — grab it pinned below. 🎁 Skool-only deal: Apify hooked up the community with 25% off any paid plan. Use this link to claim it: 👉 https://console.apify.com/sign-up?fpr=puru&couponId=25UP This is the same data layer I'm using to scrape LinkedIn, X, and company sites for the SDR team in the video. The free tier is enough to test, but if you're running this at scale, the 25% off basically pays for itself on the first campaign. Drop a comment with the team you'd build first — SDR, influencer tracking, competitive research, customer support — whichever one wins